diff --git a/.gitignore b/.gitignore index 2405a81f..a30fd144 100644 --- a/.gitignore +++ b/.gitignore @@ -26,6 +26,7 @@ .DS_Store .eslintrc.js .idea +.env .venv venv .vscode diff --git a/models/config.yaml b/models/config.yaml index 9c8ce827..00db01d1 100644 --- a/models/config.yaml +++ b/models/config.yaml @@ -45,9 +45,6 @@ .*starchat-beta: instruction_template: 'Starchat-Beta' custom_stopping_strings: '"<|end|>"' -.*(openorca-platypus2): - instruction_template: 'OpenOrca-Platypus2' - custom_stopping_strings: '"### Instruction:", "### Response:"' (?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna: instruction_template: 'Vicuna-v0' .*vicuna.*v0: @@ -152,6 +149,9 @@ instruction_template: 'Orca Mini' .*(platypus|gplatty|superplatty): instruction_template: 'Alpaca' +.*(openorca-platypus2): + instruction_template: 'OpenOrca-Platypus2' + custom_stopping_strings: '"### Instruction:", "### Response:"' .*longchat: instruction_template: 'Vicuna-v1.1' .*vicuna-33b: diff --git a/modules/GPTQ_loader.py b/modules/GPTQ_loader.py index fe5577e1..7dc20b0a 100644 --- a/modules/GPTQ_loader.py +++ b/modules/GPTQ_loader.py @@ -62,7 +62,7 @@ def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exc from safetensors.torch import load_file as safe_load model.load_state_dict(safe_load(checkpoint), strict=False) else: - model.load_state_dict(torch.load(checkpoint), strict=False) + model.load_state_dict(torch.load(checkpoint, weights_only=True), strict=False) model.seqlen = 2048 return model diff --git a/modules/training.py b/modules/training.py index b887fa47..c01f27db 100644 --- a/modules/training.py +++ b/modules/training.py @@ -544,7 +544,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en: lora_model = get_peft_model(shared.model, config) if not always_override and Path(f"{lora_file_path}/adapter_model.bin").is_file(): logger.info("Loading existing LoRA data...") - state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin") + state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin", weights_only=True) set_peft_model_state_dict(lora_model, state_dict_peft) except: yield traceback.format_exc().replace('\n', '\n\n')